A vehicle detection method and a vehicle detection system

Abstract

The application provides a vehicle detection method and a vehicle detection system, and is suitable for the technical field of intelligent traffic. The method comprises the following steps: when a vehicle enters a detection area of a lane, acquiring the position information of the vehicle in real time through a position detection device; determining the identification area where the vehicle is currently located according to the position information of the vehicle, and taking the identification area as a target identification area; sending a snapshot signal to a shooting device, so that the shooting device takes a snapshot of the vehicle in the target identification area to obtain a target image, and performs license plate recognition based on the target image. Through the embodiment of the application, the shooting device can take a snapshot in real time and acquire the license plate information of the vehicle in the current target identification area, so as to solve the problem of license plate mis-detection or missed detection caused by the front vehicle shielding the rear vehicle and the simultaneous appearance of multiple vehicle license plate information in the same identification area.

Description

Technical Field

[0001] This application belongs to the field of intelligent transportation technology, and in particular relates to a vehicle detection method and a vehicle detection system. Background Technology

[0002] Overloaded vehicles are a frequent occurrence on highways. Overloaded transport not only causes abnormal damage to roads and bridges, but also greatly increases the risk of traffic accidents, endangering people's lives and property. Utilizing information technology to control overloading has become a major approach to managing freight overloading. Among these methods, the non-stop dynamic weighing detection system on highways is an indispensable component.

[0003] However, traditional vehicle overload identification methods suffer from low accuracy due to various factors during vehicle operation, such as obstruction of following vehicles by the vehicle in front, poor lighting conditions, low license plate resolution, simultaneous appearance of license plate information from multiple vehicles, or mismatch between vehicle and lane information caused by lane changes. Summary of the Invention

[0004] In view of this, embodiments of this application provide a vehicle overload identification method, apparatus, and terminal equipment, which can improve the accuracy of vehicle detection.

[0005] A first aspect of this application provides a vehicle detection method applied to a vehicle detection system including a position detection device and a camera; wherein a plurality of identification regions are sequentially divided along the road extension direction in the detection area of ​​at least one lane, the method comprising:

[0006] When a vehicle enters the detection area of ​​the lane, the vehicle's position information is acquired in real time by the position detection device. Based on the vehicle's position information, the current recognition area of ​​the vehicle is determined in real time, and when the current recognition area is determined to be a new recognition area for the vehicle, the current recognition area is taken as the target recognition area. A capture signal is sent to the shooting device so that the shooting device can capture the vehicle in the target recognition area to obtain a target image. The license plate information of the vehicle is determined based on the acquired target images.

[0007] In one possible implementation of the first aspect, every two adjacent identification regions are close together or partially overlap.

[0008] In one possible implementation of the first aspect, determining the vehicle's license plate information based on the acquired plurality of target images includes:

[0009] From multiple target images corresponding to the same vehicle, the target image with the highest clarity and containing the license plate is determined, and the license plate is identified in the recognition area corresponding to the determined target image to determine the license plate information of the vehicle.

[0010] In one possible implementation of the first aspect, the position detection device includes a weighing device or a laser device;

[0011] The weighing device includes M sensor components arranged in parallel in each lane, and the M sensor components are divided into multiple recognition areas along the driving direction, and each recognition area includes at least two sensor components, where M is an integer greater than 2.

[0012] In one possible implementation of the first aspect, determining the current identification area of ​​the vehicle based on the vehicle's location information includes:

[0013] Based on the received location information, determine the location of the vehicle's license plate;

[0014] Based on the determined location of the vehicle's license plate, the target recognition area where the vehicle is currently located is determined.

[0015] In one possible implementation of the first aspect, determining the location of the vehicle's license plate based on the received location information includes:

[0016] Based on the received position information, determine the positions of the left and right wheels of the vehicle's front axle;

[0017] The license plate position is determined based on the positions of the left and right wheels of the first axle.

[0018] In one possible implementation of the first aspect, determining the target recognition area where the vehicle is currently located based on the license plate position includes:

[0019] Calculate the distance between the center of each recognition region and the license plate location;

[0020] The recognition region corresponding to the minimum value among the multiple distances is determined as the target recognition region.

[0021] In one possible implementation of the first aspect, when the vehicle detection system includes the weighing device, the method further includes:

[0022] When the vehicle passes the weighing device, the weighing device collects and updates the vehicle information, which includes at least one of the following: the vehicle's license plate number identified based on the target image, the number of axles, the wheelbase, and the axle load.

[0023] A second aspect of this application provides a vehicle detection system, which sequentially divides a plurality of identification areas along the road extension direction in the detection area of ​​each lane; the vehicle detection system includes:

[0024] The position detection device acquires the vehicle's position information in real time after the vehicle enters the detection area of ​​the lane;

[0025] The data processing platform is used to determine the current identification area of ​​the vehicle in real time based on the vehicle's location information, and when the current identification area is determined to be a new identification area for the vehicle, to use the current identification area as the target identification area; and to generate and send a capture signal to the shooting device.

[0026] The shooting device is used to receive the shooting signal, capture images of vehicles within the target recognition area based on the shooting signal to obtain target images, and determine the license plate information of the vehicles based on the acquired target images.

[0027] In one possible implementation of the second aspect, the shooting device determines the target image with the highest clarity and containing the license plate from multiple target images corresponding to the same vehicle, and performs license plate recognition on the recognition area corresponding to the determined target image.

[0028] A third aspect of this application provides a terminal device, the terminal device including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program to implement the steps of the vehicle detection method as described in any of the first aspects above.

[0029] A fourth aspect of this application provides a computer-readable storage medium comprising: storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the vehicle detection method as described in any of the first aspects above.

[0030] The fifth aspect of this application provides a computer program product that, when run on a terminal device, causes the terminal device to execute the vehicle detection method described in any of the first aspects above.

[0031] The beneficial effects of this application embodiment compared with the prior art are as follows: Through this application embodiment, when a vehicle enters the detection area of ​​the lane, the vehicle's position information is acquired in real time by the position detection device; based on the vehicle's position information, the current recognition area of ​​the vehicle is determined and used as the target recognition area; a capture signal is sent to the shooting device so that the shooting device captures the vehicle in the target recognition area to obtain a target image, and license plate recognition is performed based on the target image; through this application embodiment, the shooting device can capture and obtain the license plate information of the vehicle in the current target recognition area in real time, so as to solve the problem of false detection or missed detection of license plates caused by the front vehicle obscuring the rear vehicle and the simultaneous appearance of license plate information of multiple vehicles in the recognition area, thereby improving the accuracy of vehicle license plate detection. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle detection system provided in this application embodiment;

[0034] Figure 2 This is a schematic diagram illustrating the implementation process of the vehicle detection method provided in the embodiments of this application;

[0035] Figure 3 This is a schematic diagram of the identification area for vehicle detection provided in an embodiment of this application;

[0036] Figure 4 This is a schematic diagram of the sensor layout provided in an embodiment of this application;

[0037] Figure 5 This is a schematic diagram of the vehicle's driving position in the identification area provided in the embodiments of this application;

[0038] Figure 6 This is a schematic diagram of the vehicle detection system provided in the embodiments of this application;

[0039] Figure 7 This is a schematic diagram of the terminal device provided in the embodiments of this application. Detailed Implementation

[0040] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0041] Currently, utilizing information technology to combat overloading has become a major approach to managing freight overloading. Among these methods, the non-stop dynamic weighing detection system on highways is an indispensable component. The system automatically detects a vehicle's speed, axle load, number of axles, wheelbase, total weight, and transit time, automatically separating the vehicle and generating a complete weighing record. This record is then matched with evidence such as captured images of the front, body, and rear of the vehicle, as well as short videos of the detection process, to effectively manage overloading of freight vehicles. Furthermore, based on specific application needs, it can be used to manage overloaded vehicles.

[0042] In this evidence collection process, the front of the vehicle to be inspected can be captured and the license plate can be recognized by the capture signal provided by the dynamic position detection device (weighing subsystem). Multiple shooting devices (such as multiple cameras) can also be configured to capture the vehicle body and rear, as well as extract short videos of the vehicle in motion. The front-end detection software of the vehicle detection system will accurately match the license plate results, images, video information and weighing information, ultimately enabling road administration or law enforcement personnel to accurately enforce the law and collect evidence on overloaded vehicles.

[0043] Since the accuracy of license plate detection is crucial for evidence collection, detection errors can significantly hinder the process. A significant factor contributing to these errors is the division of the recognition area. Currently, a widely adopted method for dividing license plate recognition areas is based on the actual lane. When multiple license plates exist within the same recognition area corresponding to a lane, detecting the license plate of the target vehicle can lead to errors. For example, even if two license plates appear consecutively in the same scene, the output might show the license plate of a vehicle other than the target one. This can easily result in errors in the association between vehicles and license plates.

[0044] For example, during a single capture within the recognition area of ​​the same lane, if the license plate of the vehicle being detected is obscured by the vehicle in front, and there is no license plate available for recognition within the recognition area, the capturing device will output "unrecognized," resulting in the inability to detect the target vehicle. Furthermore, even after the vehicle in front leaves the capture area, because traditional zone division only captures once, the recognition area of ​​that lane will not provide a capture signal again to identify the vehicle, leading to low detection accuracy.

[0045] Based on the above statements, embodiments of this application provide a vehicle detection method that can improve the accuracy of vehicle detection systems.

[0046] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle detection system provided in this application embodiment, such as... Figure 1 As shown, when a vehicle passes through each identification area sequentially divided along the road extension direction in the vehicle detection system, the imaging device in the vehicle detection system can be triggered. The imaging device captures the vehicle that has reached the target identification area and identifies the license plate of the captured target image. By linking the target area with the imaging action of the imaging device, and identifying the license plate corresponding to the target identification area in the acquired target image, vehicle detection can be achieved. This can improve the accuracy of vehicle detection and avoid erroneous evidence information such as mismatch between vehicle information and license plate or failure to identify the license plate.

[0047] Specifically, the vehicle detection system can be configured to correspond to multiple lanes, such as... Figure 1 Lanes 1, 2, and 3 are shown. Each lane has a corresponding recognition area, which can be defined along the road's extension direction or the vehicle's travel direction. Each lane's recognition area is equipped with sensors and other detection devices. Each lane can also correspond to a camera device, such as camera 1 for lane 1, camera 2 for lane 2, and camera 3 for lane 3. This camera device is used to capture images of vehicles within the target area after receiving capture information, obtaining target images. These target images are used to recognize vehicle license plates, thereby achieving vehicle detection.

[0048] based on Figure 1 The application scenario shown below will be further explained in detail through specific implementation methods to illustrate the vehicle detection process.

[0049] Please see Figure 2 , Figure 2 This is a schematic diagram illustrating the implementation flow of the vehicle detection method provided in this application embodiment. The executing entity of this vehicle detection method can be a vehicle detection system, which may include a position detection device and a camera; in the lane corresponding to the vehicle detection system, multiple identification areas are sequentially divided along the road extension direction in the detection area of ​​at least one lane. For example... Figure 2 As shown, the vehicle detection method may include:

[0050] S201, when a vehicle enters the detection area of ​​the lane, the vehicle's position information is obtained in real time through the position detection device.

[0051] In some embodiments, a detection zone is provided in each lane, such as Figure 1 As shown; the detection area is divided into multiple recognition areas along the road's extension direction, such as... Figure 3 As shown, lane 1 includes recognition area 1-1, recognition area 1-2 and recognition area 1-3, lane 2 includes recognition area 2-1, recognition area 2-2 and recognition area 2-3, and lane 3 includes recognition area 3-1, recognition area 3-2 and recognition area 3-3.

[0052] It should be noted that, Figure 3 This is merely an example illustrating how the detection area is divided along the road direction. The number of recognition areas divided in the detection area of ​​each lane can be set according to requirements, and the number of recognition areas divided between different lanes can also be different. Here, there is no specific limitation on the specific method and number of recognition areas divided along the road extension direction in the detection area.

[0053] In some embodiments, the position detection device includes a weighing device or a laser device; wherein the weighing device includes M sensor components arranged in parallel in each lane, the M sensor components are divided into multiple recognition areas along the driving direction, and each recognition area includes at least two of the sensor components, where M is an integer greater than 2.

[0054] For example, the weighing device may include a weighing sensor. The weighing device and the laser device may be installed underground in the lane detection area. Figure 4 As shown, M sensor assemblies are arranged in parallel within the detection area of ​​each lane; the sensor assembly may include multiple weighing sensors, and each identification area may include at least two sets of its sensing components.

[0055] like Figure 4 As shown, each sensor assembly in each lane has corresponding identification information for its load cells. For example, load cells 1, 2, and 3 are arranged in lane 1; and load cells 4, 5, and 6 are arranged in lane 2. Each sensor assembly in each lane can have one or more load cells. In addition, the sensor assemblies arranged along the driving direction in each lane also have identification information, such as group 1, group 2, group 3, etc. That is, the identification information of the load cells in each identification area corresponds to the identification area.

[0056] For example, the location detection device may also include an abnormal driving detection sensor and a ground inductive loop; wherein, the abnormal driving detection sensor is used to identify abnormal information during the vehicle's driving process, such as speeding; and the ground inductive loop is used to confirm the process of the vehicle from entering the identification area to leaving the identification area.

[0057] It should be noted that, Figure 4 This is merely an example illustrating the arrangement of the sensor components in the position detection device within the recognition area of ​​each lane; this arrangement is not limited to... Figure 4 The method shown can be any pre-deployed method. Therefore, this embodiment of the application does not require additional hardware. Based on the existing sensor layout structure and the correspondence between the recognition areas of each lane division, as well as the signal characteristics triggered by the sensors, the vehicle's position information can be determined. Figure 4 This is merely an illustrative example and does not constitute a limitation on the sensor arrangement in the embodiments of this application.

[0058] For example, since each lane's detection area is equipped with a weighing device or a laser device, each device has corresponding identification information; after a vehicle enters the detection area, it triggers the weighing device or laser device, and based on the identification information of the triggered device, the vehicle's position during travel is determined by a position detection device; simultaneously, the vehicle's trajectory within the lane's detection area can be determined based on the periodically acquired identification information of the triggered devices. Furthermore, in some other embodiments, laser equipment can be used to track vehicles entering the detection area in real time.

[0059] For example, the location information may be the identification information of the triggered weighing device or laser device, or the location information of the triggered weighing device or laser device.

[0060] S202, based on the vehicle's location information, determine the current identification area where the vehicle is located in real time, and when the current identification area is determined to be a new identification area for the vehicle, use the current identification area as the target identification area.

[0061] In some embodiments, after determining the vehicle's location information, the vehicle detection system can determine the recognition area where the vehicle is located based on that location information. When the current recognition area is determined to be a new recognition area for the vehicle, it is used as the target recognition area to achieve vehicle recognition within that area, thereby improving the accuracy of vehicle recognition. This target recognition area is used as a marker object in subsequent steps for target image recognition, determining the region to be recognized in the target image.

[0062] For example, the location information determined by the vehicle detection system can be the identification information of the weighing device or laser device triggered after the vehicle enters the detection area, or the location information of the triggered weighing device or laser device. Thus, the current identification area of ​​the vehicle can be determined based on the correspondence between the identification information or location information of the weighing device or laser device and the identification area.

[0063] like Figure 5 As shown in Figure (a), when a vehicle enters the detection area, it triggers the weighing device or laser device arranged in the detection area. The weighing device or laser device generates trigger information, which may include the identification information or location information of the triggered weighing device or laser device. Based on the identification information or location information, the location information of the vehicle is determined. According to the location information of the vehicle, the identification area where the vehicle is located in the detection area is determined, and the identification area is used as the target identification area for the next step of image recognition.

[0064] For example, each time a vehicle enters a recognition area, the target recognition area is confirmed; for instance, when a vehicle enters recognition area 1-1, recognition area 1-1 is confirmed as the target recognition area; when a vehicle enters recognition area 1-2 at a certain moment, recognition area 1-2 is confirmed as the target recognition area; when a vehicle changes lanes from recognition area 1-1 in lane 1 to recognition area 2-2 in lane 2, recognition area 2-2 is determined as the target recognition area. Figure 5 As shown in Figure (b) of the document.

[0065] In this embodiment, the detection area in the lane is finely divided by the position of the triggered weighing device or laser device, and multiple recognition areas are divided in the direction of travel. Each vehicle entering a recognition area triggers the detection, allowing for further filtering of the collected information during subsequent identification. Compared to traditional recognition areas and triggering methods, this embodiment improves the sufficiency and reliability of information during vehicle detection, making it easier to determine license plate recognition and confirmation in the subsequent process, thereby improving the accuracy and reliability of vehicle detection.

[0066] In some embodiments, determining the current identification area of ​​the vehicle based on the vehicle's location information includes:

[0067] Based on the received location information, the location of the vehicle's license plate is determined; based on the determined location of the vehicle's license plate, the target recognition area where the vehicle is currently located is determined.

[0068] For example, after a vehicle enters any recognition area within the detection area, the weighing device in that recognition area is triggered by the front tires or the laser device is triggered by the front of the vehicle; thus, the position of the license plate corresponding to the front license plate of the vehicle can be further determined based on the position of the triggered weighing device or laser device, and then the target recognition area where the vehicle is located can be determined based on the position of the license plate.

[0069] For example, when a vehicle is driving in the detection area, each time a weighing device or laser device in a recognition area is triggered, the position information of the vehicle's license plate is calculated based on the determined position information of the vehicle. The target recognition area where the vehicle is currently located is determined based on the position information of the license plate after each trigger.

[0070] In some embodiments, determining the location of the vehicle's license plate based on the received location information includes:

[0071] Based on the received location information, the positions of the left and right wheels of the vehicle's front axle are determined; based on the positions of the left and right wheels of the front axle, the position of the license plate is determined.

[0072] For example, the distance between the front license plate and the vehicle's front axle is fixed, or within a certain range, or the distance can be determined based on different vehicle models. Based on the position information determined by the weighing device or laser device in the detection area triggered by the front wheels, the positions of the left and right wheels on the front axle can be determined. The center position of the line connecting the left and right wheels on the front axle is taken, and combined with the distance between the license plate and the front axle, the license plate position is calculated. This allows for further precision in identifying the vehicle's license plate within the target recognition area, i.e., the vehicle's current location within the target recognition area.

[0073] like Figure 5 As shown in Figure (b), when a vehicle enters identification area 1-1, the weighing device or laser device in that identification area is triggered. Based on the triggering signal fed back by the triggered weighing device and laser device, the vehicle's position information can be determined. Based on this position information, the license plate position information can be further determined, and the target identification area where the vehicle is located can be determined as identification area 1-1 based on the license plate position. When the vehicle moves from identification area 1-1 into identification area 2-2, the weighing device or laser device in identification area 2-1 may be triggered. At this time, the vehicle may cross two identification areas (such as identification area 1-1 and identification area 2-1). At this time, it is necessary to confirm the license plate position based on the vehicle's position information, and then confirm whether the target identification position where the vehicle is currently located is identification area 1-1 or identification area 1-2 based on the license plate position.

[0074] For example, when two vehicles appear in the same lane, the target recognition areas of the two vehicles can be distinguished based on the calculated license plate position. This allows subsequent steps to collect images based on their respective target recognition areas, preventing errors such as mismatch between vehicles and license plates.

[0075] For example, after a target vehicle enters the detection area, if there are obstructing vehicles in front, the image acquired in subsequent steps may not contain the target vehicle's license plate or may contain the license plates of other vehicles, which could easily lead to unrecognized or mismatched information. By setting multiple recognition areas in the detection area of ​​the same lane in this application embodiment, the image acquisition of the target vehicle can continue after the target vehicle enters the next recognition area, thereby improving the reliability of image data acquisition.

[0076] In some embodiments, determining the target recognition area where the vehicle is currently located based on the license plate position includes:

[0077] Calculate the distance between the center of each recognition region and the license plate location; determine the recognition region corresponding to the minimum value among the multiple distances as the target recognition region.

[0078] For example, when determining the target recognition area where the vehicle is located, the distance between the license plate and the center of each recognition area can be calculated based on the license plate position. Based on this distance, the recognition area whose center is closest to the license plate position is taken as the target recognition area.

[0079] For example, when a vehicle is at the intersection of recognition area 1-1 and recognition area 1-2 in lane 1, or has just entered recognition area 1-2 from recognition area 1-1, the target recognition area of ​​the vehicle whose center is closest to the license plate can be determined based on the distance between the license plate position and the center of recognition area 1-1 and recognition area 1-2, respectively.

[0080] For example, when a vehicle changes lanes from recognition area 1-1 to recognition area 2-2, the area it crosses may include recognition areas 1-1, 2-1, and 2-2. Therefore, based on the license plate position, the distances to the centers of recognition areas 1-1, 2-1, and 2-2 can be calculated respectively, determining the target recognition area for the vehicle whose center is closest to the license plate position. This allows for precise lane number and license plate location based on the vehicle's trajectory and position information located by weighing or laser devices, improving the accuracy of vehicle detection.

[0081] S203, send a capture signal to the shooting device so that the shooting device can capture images of vehicles in the target recognition area to obtain target images.

[0082] S204, determine the license plate information of the vehicle based on the acquired multiple target images.

[0083] In some embodiments, when a vehicle enters the detection area and triggers the weighing device or laser device in the detection area, the vehicle detection system sends a capture signal to the imaging device through the weighing device or laser device. The capture signal may include the label corresponding to the target recognition area where the vehicle is currently located, such as recognition area 1-2. After receiving the capture signal, the imaging device captures an image of the vehicle within the target recognition area to obtain a target image, and the vehicle detection system identifies the license plate in the target image.

[0084] For example, the target image can be marked with a number indicating the target recognition area where the vehicle is located; the vehicle detection system can then identify the license plate within the target recognition area of ​​the target image based on this number. This can improve the accuracy and efficiency of the recognition.

[0085] For example, when a vehicle passes through the detection area, the vehicle detection system will establish vehicle information and update the vehicle information in real time, calculate the position of the vehicle's first axle, locate the left and right wheels of the vehicle's first axle, and determine whether the vehicle has reached the recognition area that needs to be captured.

[0086] For example, when a vehicle travels around S, such as Figure 5 As shown in Figure (b), a mismatch between license plate position and lane information can lead to matching errors. This application addresses this by locating the vehicle's first axle position and updating its location information in real time. Even if a vehicle travels in an S-shape across lanes, the vehicle detection system's collector will determine the license plate's location area based on the vehicle's trajectory and first axle position. It can then send capture signals with the same vehicle ID and area label, improving the recognition rate through vehicle ID and data matching. Figure 5 As shown in (b), when the license plate is in the recognition area 2-2, the collector will send a trigger signal to the camera 2. The camera captures the target image and the recognition result (detection result) of the license plate recognition of the target image, so that the vehicle ID can be matched with the weighing data.

[0087] In some embodiments, the capturing device includes multiple snapshot devices, each snapshot device being configured corresponding to the recognition area; the capturing device captures images of vehicles within the target recognition area based on the snapshot signal, including:

[0088] After receiving the capture signal, the shooting device determines the capture device corresponding to the target recognition area, instructs the determined capture device to capture the target recognition area, and generates the target image.

[0089] For example, such as Figure 1As shown, each lane's detection area can correspond to one capture device. In addition, if the actual application scenario requires it, such as for the detection of long vehicles like trailers, the recognition area divided within the detection area may be long along the road direction. In this case, corresponding capture devices can be set up on different recognition areas in a lane. For example, one capture device can be set up in the current recognition area, and another capture device can be set up in the next adjacent recognition area in the same lane as the current recognition area to improve both detection accuracy and detection efficiency.

[0090] It should be noted that the capture signal may contain a label of the target recognition area, and the target image obtained by the capturing device from the vehicle in the target recognition area may also contain the label. Furthermore, a local image area corresponding to the target recognition area may also be marked in the target image. The vehicle detection system can recognize the license plate based on the label and the local image area.

[0091] In some embodiments, determining the vehicle's license plate information based on the acquired multiple target images includes:

[0092] From multiple target images corresponding to the same vehicle, the target image with the highest clarity and containing the license plate is determined, and the license plate is identified in the recognition area corresponding to the determined target image to determine the license plate information of the vehicle.

[0093] For example, since the detection area for each lane is divided into multiple recognition areas, and a vehicle passing through each recognition area triggers a capture signal from a weighing device or laser device, the capturing device captures images for each recognition area, resulting in multiple target images of the same vehicle. The image with the highest clarity and containing the license plate is then selected from these multiple target images for license plate recognition. This improves the accuracy of vehicle detection and ensures the reliability of authentication information. In other embodiments, the license plate information obtained from recognizing each target image can be used first, and then the image with the highest clarity and containing the license plate can be selected from the multiple target images. The license plate information corresponding to the selected image with the highest clarity and containing the license plate can then be used as the vehicle's license plate information. This embodiment does not limit this approach.

[0094] In some embodiments, when the vehicle detection system includes the weighing device, the method further includes:

[0095] When the vehicle passes the weighing device, the weighing device collects and updates the vehicle information, which includes at least one of the following: the vehicle's license plate number identified based on the target image, the number of axles, the wheelbase, and the axle load.

[0096] For example, the vehicle detection system can calculate the weight information after the vehicle passes through the weighing device in the detection area. This weight information may have the same label as the captured target image (the label of the target recognition area) and be sent to the host computer. The host computer can match the recognition results of the selected license plates with the vehicle weight data to obtain authentication information, thereby outputting the result of completing the evidence chain.

[0097] In this embodiment, when a vehicle passes through the detection area, it triggers sensors with different identification information. By collecting the number of trigger points of the sensors, the vehicle's trajectory and the position of the first axle are calculated, and the positions of the left and right wheels of the first axle are determined. Then, the position of the license plate is deduced. When the license plate position is successively within the identification areas 1-1, 1-2, and 1-3 in the same lane or in identification areas in different lanes, the vehicle detection system will send a corresponding capture signal to the shooting device. The capture signal will carry the corresponding lane number, area label, vehicle ID, and other information. The shooting device will output three capture photos to the host computer. The host computer will filter and select the photos with license plate recognition results as the correct recognitions. Then, it will bind the weighing information and output the correct matching result.

[0098] In this embodiment, by using a refined division of the detection area and combining it with a weighing logic algorithm, vehicle information is tracked in real time, and the license plate position within the recognition area is accurately located. Multiple captures and multiple recognitions can greatly avoid problems such as unrecognized vehicles due to obstruction from the front and rear vehicles or lighting angles, thus improving the recognition accuracy.

[0099] Corresponding to the method in the above embodiments, Figure 6 A structural block diagram of the vehicle detection system provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown. Figure 6 The vehicle detection system in the example can be the entity that executes the vehicle detection method provided in the foregoing embodiments.

[0100] Reference Figure 6 The vehicle detection system may include:

[0101] The position detection device 61 acquires the vehicle's position information in real time after the vehicle enters the detection area of ​​the lane.

[0102] The data processing platform 62 is used to determine the current identification area of ​​the vehicle in real time based on the vehicle's location information, and when the current identification area is determined to be a new identification area for the vehicle, to use the current identification area as the target identification area; and to generate and send a capture signal to the shooting device.

[0103] The shooting device 63 is used to receive the shooting signal, capture images of vehicles within the target recognition area according to the shooting signal, and determine the license plate information of the vehicles based on the acquired multiple target images.

[0104] In some embodiments, the imaging device determines the target image with the highest clarity and containing the license plate from multiple target images corresponding to the same vehicle, and performs license plate recognition on the recognition area corresponding to the determined target image.

[0105] The process by which each module in the vehicle overload detection device provided in this application implements its respective function can be referred to the foregoing. Figure 1 The description of the illustrated embodiment will not be repeated here.

[0106] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0107] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0108] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0109] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0110] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first," "second," etc., are used in the text to describe various elements in some embodiments of this application, these elements should not be limited by these terms. These terms are merely used to distinguish one element from another. For example, a first table may be named a second table, and similarly, a second table may be named a first table, without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0111] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0112] Figure 7 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. For example... Figure 7 As shown, the terminal device 7 of this embodiment includes: at least one processor 70 ( Figure 7 (Only one is shown in the image) A memory 71 stores a computer program 72 that can run on the processor 70. When the processor 70 executes the computer program 72, it implements the steps in the various embodiments of the potential customer identification methods described above, for example... Figure 2 Steps 201 to 203 are shown. Alternatively, when the processor 70 executes the computer program 72, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 6 The functions of modules 61 to 63 are shown.

[0113] The terminal device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will understand that... Figure 7 This is merely an example of terminal device 7 and does not constitute a limitation on terminal device 7. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input transmitting devices, network access devices, buses, etc.

[0114] The processor 70 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0115] In some embodiments, the memory 71 may be an internal storage unit of the terminal device 7, such as a hard disk or memory of the terminal device 7. The memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device 7. Furthermore, the memory 71 may include both internal and external storage units of the terminal device 7. The memory 71 is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory 71 can also be used to temporarily store data that has been sent or will be sent.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0117] This application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, it causes the terminal device to implement the steps in any of the above method embodiments.

[0118] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0119] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0120] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0121] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0122] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A vehicle inspection method, characterized in that, Applied to a vehicle detection system including a position detection device and a camera; in the detection area of ​​at least one lane, multiple recognition areas are sequentially divided along the road extension direction; The vehicle detection method includes: Once a vehicle enters the detection area of ​​the lane, the vehicle's position information is acquired in real time through the position detection device. Based on the vehicle's location information, the current identification area of ​​the vehicle is determined in real time, and when the current identification area is determined to be a new identification area for the vehicle, the current identification area is taken as the target identification area. Send a capture signal to the shooting device so that the shooting device can capture images of vehicles within the target recognition area to obtain target images; The license plate information of the vehicle is determined based on multiple target images of the same vehicle acquired; The method further includes: Each time a vehicle enters a recognition area, the target recognition area is confirmed once, triggering a capture signal. The capturing device captures images of each recognition area entered by the vehicle based on the capture signal, obtaining multiple target images of the same vehicle. These multiple target images are used for filtering when determining the vehicle's license plate information in the future, to determine the target image with the license plate.

2. The method as described in claim 1, characterized in that, Each pair of adjacent identification regions is either close together or partially overlaps.

3. The method as described in claim 1, characterized in that, Determining the vehicle's license plate information based on the acquired multiple target images includes: From multiple target images corresponding to the same vehicle, the target image with the highest clarity and containing the license plate is determined, and the license plate is identified in the recognition area corresponding to the determined target image to determine the license plate information of the vehicle.

4. The method as described in claim 1, characterized in that, The position detection device includes a weighing device or a laser device; The weighing device includes M sensor components arranged in parallel in each lane, and the M sensor components are divided into multiple recognition areas along the driving direction, and each recognition area includes at least two sensor components, where M is an integer greater than 2.

5. The method as described in claim 1, characterized in that, Determining the current identification area of ​​the vehicle based on its location information includes: Based on the received location information, determine the location of the vehicle's license plate; Based on the determined location of the vehicle's license plate, the target recognition area where the vehicle is currently located is determined.

6. The method as described in claim 5, characterized in that, Determining the location of the vehicle's license plate based on the received location information includes: Based on the received position information, determine the positions of the left and right wheels of the vehicle's front axle; The license plate position is determined based on the positions of the left and right wheels of the first axle.

7. The method as described in claim 5, characterized in that, Determining the target recognition area where the vehicle is currently located based on the license plate position includes: Calculate the distance between the center of each recognition region and the license plate location; The recognition region corresponding to the minimum value among the multiple distances is determined as the target recognition region.

8. The method as described in claim 4, characterized in that, When the vehicle detection system includes the weighing device, the method further includes: When the vehicle passes the weighing device, the weighing device collects and updates the vehicle information, which includes at least one of the following: the vehicle's license plate number identified based on the target image, the number of axles, the wheelbase, and the axle load.

9. A vehicle detection system, characterized in that, In the detection area of ​​each lane, multiple recognition areas are sequentially divided along the direction of road extension; The vehicle detection system includes: The position detection device acquires the vehicle's position information in real time after the vehicle enters the detection area of ​​the lane; The data processing platform is used to determine the current identification area of ​​the vehicle in real time based on the vehicle's location information, and when the current identification area is determined to be a new identification area for the vehicle, to use the current identification area as the target identification area; and to generate and send a capture signal to the shooting device. The shooting device is used to receive shooting signals, capture images of vehicles within the target recognition area based on the shooting signals, and determine the license plate information of the vehicles based on the acquired multiple target images. Each time a vehicle enters a recognition area, the target recognition area is confirmed and a capture signal is triggered. The capturing device captures images of each recognition area entered by the vehicle based on the capture signal, resulting in multiple target images of the same vehicle. These multiple target images are used to filter and determine the target image containing the license plate when determining the vehicle's license plate information later.

10. The vehicle detection system as described in claim 9, characterized in that, The imaging device identifies the target image with the highest clarity and containing the license plate from multiple target images corresponding to the same vehicle, and performs license plate recognition on the recognition area corresponding to the identified target image.

Images